RAG on living data
Configured with Chain Retrieval Qa, Chat Trigger, Document Default Data Loader, Embeddings Open Ai, and additional nodes. Review the connections and setup before adapting this template.
Node categories in this workflow
- AI & models
- Transform
- Routing
- Trigger
- Data store
- Integration
- Files / media
Icons describe general node roles, inferred from node types. Inspect the parameters for the configured action.
Drag to pan; use + and − to zoom. Reconstructed from the exported node positions; nothing runs here. Dashed lines represent non-main connections. Full node names and notes appear below.
How it works
The exported workflow contains the following configured nodes. Their connections are shown above; inspect the JSON for the complete logic, expressions, and external actions.
| Node | Category | Type | Operation |
|---|---|---|---|
| Embeddings OpenAI | AI & models | Embeddings Open Ai | See node parameters |
| Token Splitter | Transform | Text Splitter Token Splitter | See node parameters |
| Loop Over Items | Routing | Loop Over Items | See node parameters |
| Question and Answer Chain | AI & models | Chain Retrieval Qa | See node parameters |
| Vector Store Retriever | AI & models | Retriever Vector Store | See node parameters |
| OpenAI Chat Model | AI & models | OpenAI Chat Model | See node parameters |
| When chat message received | Trigger | Chat Trigger | See node parameters |
| Schedule Trigger | Trigger | Schedule Trigger | See node parameters |
| Limit | Transform | Limit | See node parameters |
| Limit1 | Transform | Limit | See node parameters |
| Delete old embeddings if exist | Data store | Supabase | delete |
| Get page blocks | Integration | Notion | block / getAll |
| Default Data Loader | Files / media | Document Default Data Loader | See node parameters |
| Input Reference | Routing | No Op | See node parameters |
| Notion Trigger | Trigger | Notion Trigger | See node parameters |
| Get updated pages | Integration | Notion | databasePage / getAll |
| Supabase Vector Store1 | Data store | Vector Store Supabase | See node parameters |
| Supabase Vector Store | Data store | Vector Store Supabase | See node parameters |
| Concatenate to single string | Transform | Summarize | See node parameters |
Setup
- Download the JSON and import it into an isolated n8n instance. Leave the workflow inactive.
- Connect your own credentials through n8n’s credential store. Replace
REPLACE_WITH_*values with your resource identifiers. - Inspect API destinations, Code nodes, database queries, file paths, and outbound actions.
- Run with synthetic data and harmless destinations. Enable triggers only after checking the actual outputs.
Requirements
An n8n instance with the listed node types and compatible versions. Service-connected workflows may require accounts, credentials, or paid APIs.
Credential types declared in the source
notionApiopenAiApisupabaseApi
Workflow notes
Switch trigger (optional)
Switch trigger (optional)
If you are on the cloud plan, consider switching to the Notion Trigger Node instead, to save on executions.
Adjust chunk size and overlap
Adjust chunk size and overlap
For more accurate search results, increase the overlap. For the text-embedding-ada-002 model the chunk size plus overlap must not exceed 8191
Sticky Note23
This placeholder serves as a reference point so it is easier to swap the data source with a different service
Sticky Note24
All chunks of a previous version of the document are being deleted by filtering the meta data by the given ID
Sticky Note25
Reduce the active streams/items to just 1 to prevent the following nodes from double-processing
Sticky Note26
Retrieve all page contents/blocks
Sticky Note28
Embed item and store in Vector Store. Depending on the length the content is being split up into multiple chunks/embeds
Sticky Note30
Simple chat bot to ask specific questions while having access to the context of the Notion Knowledge Base which was stored in the Vector Store
Sticky Note31
Model used for both creating and reading embeddings
Sticky Note32
Process each page/document separately.
Sticky Note29
Store additional meta data with each embed, especially the Notion ID, which can be later used to find all belonging entries of one page, even if they got split into multiple embeds.
Sticky Note33
Using a manual approach for polling data from Notion for more accuracy.
Select Database
Select Database
Choose the database which represents your Knowledge Base
Sticky Note35
Combine all contents to a single text formatted into one line which can be easily stored as an embed
RAG on living data
RAG on living data
Purpose and structure
This folder contains the RAG on living data workflow. Its executable nodes use chainRetrievalQa, chatTrigger, documentDefaultDataLoader, embeddingsOpenAi, limit, lmChatOpenAi, noOp, notion, notionTrigger, retrieverVectorStore, scheduleTrigger, splitInBatches, summarize, supabase, textSplitterTokenSplitter, vectorStoreSupabase. The table and connection map below are derived from the JSON, not an inferred guarantee of behavior.
Setup
Import inactive. Configure your own credentials and replace REPLACE_WITH_* values. Review external destinations and Code nodes before running.
Entry points
When chat message received, Schedule Trigger, Notion Trigger
Verification
Sanitized source candidate; not runtime-tested. This overview is generated from node metadata. Read the folder README for the connection map, credential types, and license.
Attribution
https://github.com/Zie619/n8n-workflows/blob/94007c1445d9258a7da116646b79473e7c7c3282/workflows/Limit/1527_Limit_Schedule_Automation_Scheduled.json MIT; preserve source notices.